AI Agents news and analysis on Web Pulse: 36286 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
A developer published a postmortem on a merge-gate failure class in which an automated judge scored an AI agent's transcript narrative instead of the actual git diff, allowing a schema-widening contract change to pass as…
Theoretical computer scientist Scott Aaronson, who previously held a "conservative, skeptical position" on self-improving AI, said in a blog post published Tuesday that he has updated his view and that humanity is "certa…
An analysis of 14,767 arXiv evaluation-resource papers published between 2022 and 2026 found that LLM benchmarks are shifting toward action, interaction, and professional-use tasks, with LLM-based scoring increasingly us…
The new BioPhys-Bridge benchmark, a 500-case, 1,517-task dataset for physics-grounded biological reasoning, shows state-of-the-art LLMs top out at an evidence-retrieval F1 of just 0.360, with DeepSeek-V4-Flash leading an…
Alibaba's Qwen released Qwen 3.8 Omni Flash, a 3.8-billion-parameter model that natively integrates text, vision, and audio processing in a single low-latency architecture. The model is positioned to run fully local, rea…
Bend, a high-level programming language that compiles mathematically verified code to run natively and in parallel on both CPUs and GPUs without manual multi-threading, is pitched as a constraint layer for LLM agents gen…
A developer has published an AI workflow that uses Anthropic's Claude Code `/loop` scheduler and a `CLAUDE.md` system prompt to automatically identify and update liquidation-cascade trading criteria on a monthly basis. T…
Gupta Abhishek Premkumar published a developer guide to building and deploying Model Context Protocol (MCP) servers, an open JSON-RPC standard for connecting LLM-based AI assistants to external tools, APIs, and data sour…
A non-engineer growth marketer at Publora described building three Claude Code routines to automate a 10 a.m. analytics brief, a Monday/Wednesday/Friday content-idea backlog, and a twice-daily Hacker News digest. The rou…
Groundcover is evaluating TypeSafe's newly released Jev model for AI observability, testing whether its parallel-sampler architecture and reinforcement learning for calibrated decisions can classify agent trace outcomes …
Google has filed a patent for a system that uses a generative AI model to automatically find and extract one-time login codes from a user's Gmail inbox and return them to the requesting device. The patent describes a cli…
A developer behind the open-source pi-box project demonstrated a pi agent running inside an AgentVM virtual machine autonomously installing and launching the game Doom, with the Freedoom splash screen appearing in the El…
A new Nature paper by Jiacheng Miao, Joe R. Davis, Yaohui Zhang, Jonathan K. Pritchard, and James Zou introduces Paper2Agent, an automated framework that converts research papers into artificial intelligence agents. Pape…
A developer proposes a four-file take-home contract for evaluating AI engineering candidates, arguing that green test suites and polished agent demos no longer prove a candidate understands system constraints. The propos…
TypeSafe AI's Jev became the fastest-adopted model in AI Gateway history, reaching more than twice as many paid teams within 24 hours of its September 15 launch as any previous model launch, according to Vercel. By hour …
Hamel Husain and Shreya Shankar published an AI Evals FAQ distilling the most common questions from teaching 700+ engineers and product managers about AI evaluation. The guide distinguishes model benchmarks such as GPQA …
Epoch AI launched Benchmark Reviews on September 17th and classified nine of its first 15 reviewed benchmark versions as Flawed, four as Verified, and two as Not Enough Info, flagging defects in tests including SWE-bench…
Salesforce and Google Cloud announced an expanded partnership at Dreamforce 2026 that runs Salesforce infrastructure on Google Cloud via Hyperforce and connects Salesforce's Model Context Protocol-based architecture to G…
Geoffrey Hinton, the Nobel Prize-winning computer scientist known as the "Godfather of AI," said Wednesday that US lawmakers have "maybe a year, but not much more than a year" to regulate advanced AI before it becomes "o…
A benchmark of frontier models on production-grade CAD assembly design found none reached the 60% pass threshold as of September 16, 2026, with GPT 6 (Astra, Codex at max) scoring highest at 74% ± 8% on Task Family B but…